swift-1.5-iq2_xs
LM-STUDIO UNKNOWNNov 14, 2026 · AMD Ryzen 5 5600X 6-Core Processor
GPT-OSS-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
96 vs 93
Hardware Fit
94 vs 92
Quality Score
97 vs 93
Hardware
swift-1.5-iq2_xs GPT-OSS-20B:20b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ i7-14700F
Cores1228
RAM47 GB128 GB
GPUAD106 [GeForce RTX 4060 Ti]NVIDIA GeForce RTX 5080
OSArch LinuxMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
swift-1.5-iq2_xs GPT-OSS-20B:20b
Tokens/sec60.0178.6
First chunk2 ms695 ms
TTFT2.6 s1.4 s
Load timeN/A31.2 s
Memory usage0.9 GB11.9 GB
Memory %2%9%
HW Fit Score Breakdown
swift-1.5-iq2_xs
Speed
50/50
TTFT
14/20
Memory
30/30
GPT-OSS-20B:20b
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
swift-1.5-iq2_xs
Reasoning
20/20
Coding
19/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
GPT-OSS-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest